Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2270. Min Act: -0.0000

Data Index: 155279 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2209. Min Act: -0.0000

Data Index: 354787 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1727. Min Act: -0.0000

Data Index: 219528 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1796. Min Act: -0.0000

Data Index: 234010 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1678. Min Act: -0.0000

Data Index: 521926 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1219679 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1804085 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1863453 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1564567 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1070214 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1509. Min Act: -0.0000

Data Index: 52783 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1803973 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1500336 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1232028 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1026284 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1482. Min Act: -0.0000

Data Index: 288816 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1372. Min Act: -0.0000

Data Index: 167071 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1162036 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1913327 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1542904 (The Pile)

Max Activating Token Index: 299